instrumentar-fase

instrumentar-fase is a command for Claude Code from luanpdd/kit-mcp. It costs 43 tokens per session (2,143 once invoked), scanned A, original, MIT.

A command that creates an instrumentation plan for each implementation plan, covering traces, standard attributes, events, and validation.

In plain words
What is it for?
Use it after planning a phase to document the telemetry requirements that later implementation and observability work must satisfy.
Why use it?
It defines what observability should be added before coding begins, so the executor has a clear contract to follow.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: positional $N argument.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is - Skill [`structured-events`](../skills/structured-events/SKILL.md) — campos canônicos.

Good fit Use it after planning a phase to document the telemetry requirements that later implementation and observability work must satisfy.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/luanpdd/kit-mcp
agentmods
npx agentmods add commands/luanpdd/kit-mcp/instrumentar-fase

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for instrumentar-fase

README.md
[![agentmods](https://agentmods.dev/badge/commands/luanpdd/kit-mcp/instrumentar-fase/github.svg)](https://agentmods.dev/commands/luanpdd/kit-mcp/instrumentar-fase)
Your own site
<a href="https://agentmods.dev/commands/luanpdd/kit-mcp/instrumentar-fase"><img src="https://agentmods.dev/badge/commands/luanpdd/kit-mcp/instrumentar-fase/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for instrumentar-fase

Your own site · 80×15
<a href="https://agentmods.dev/commands/luanpdd/kit-mcp/instrumentar-fase"><img src="https://agentmods.dev/badge/commands/luanpdd/kit-mcp/instrumentar-fase.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,143 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00043 $0.02143
Opus 5 $0.00022 $0.01071
Sonnet 5 $0.00009 $0.00429
Haiku 4.5 $0.00004 $0.00214

Measured 6d ago against content hash f722e4c86acf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

instrumentar-fase scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

kit/commands/instrumentar-fase.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cria/Atualiza:

  • .planning/phases/<N>/<padded>-PLAN-<NN>-INSTRUMENTATION.md por plano

Após: o user tem o contrato de instrumentação que o executor (e o observability-instrumenter) devem cumprir durante /executar-fase.

Pré-requisito: /planejar-fase <N> já rodou. Existem <padded>-PLAN-<NN>-*.md em .planning/phases/<N>/.

Skill consultada: observability-driven-development — 4 perguntas pré-PR canônicas.

1. Parsear argumentos

PHASE_NUM=$(echo "$ARGUMENTS" | awk '{print $1}')
PLAN_NUM=$(echo "$ARGUMENTS" | awk '{print $2}')

if [ -z "$PHASE_NUM" ]; then
  echo "Uso: /instrumentar-fase <N> [<NN>]"
  echo "Ex.: /instrumentar-fase 30        # todos os planos da Phase 30"
  echo "Ex.: /instrumentar-fase 30 01     # só Plano 01 da Phase 30"
  exit 1
fi

2. Detectar phase_dir + planos

PHASE_STATE=$(node "./.claude/framework/bin/tools.cjs" init phase-op "$PHASE_NUM")
PHASE_DIR=$(echo "$PHASE_STATE" | jq -r .phase_dir)

if [ "$PHASE_DIR" = "null" ] || [ ! -d "$PHASE_DIR" ]; then
  echo "Fase $PHASE_NUM ainda não foi planejada. Rode /planejar-fase $PHASE_NUM primeiro."
  exit 1
fi

# PT-BR: descobrir PLAN.md(s) — exclui já-instrumentados
if [ -n "$PLAN_NUM" ]; then
  PLANS=("$PHASE_DIR"/*-PLAN-${PLAN_NUM}-*.md)
else
  PLANS=("$PHASE_DIR"/*-PLAN-*.md)
fi

3. Para cada plano, gerar INSTRUMENTATION.md

Para cada PLAN_FILE:

PADDED=$(basename "$PLAN_FILE" | grep -oE '^[0-9]+')
NN=$(basename "$PLAN_FILE" | grep -oE 'PLAN-[0-9]+' | grep -oE '[0-9]+')
OUT_FILE="$PHASE_DIR/${PADDED}-PLAN-${NN}-INSTRUMENTATION.md"

# PT-BR: não sobrescrever se já existe
if [ -f "$OUT_FILE" ]; then
  echo "Já existe: $OUT_FILE — pulando"
  continue
fi

Read the full file on GitHub · 201 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 201 lines · 43 tokens per session scan A f722e4c86acf

Subscribe to this mod's changes

instrumentar-fase is a command published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed 3d ago), licensed MIT. It adds 43 tokens to every session and 2,143 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.